6 papers
DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination
Yi Xie, Zhanke Zhou, Chentao Cao +2
Multi-agent large language model (LLM) systems often fail to reliably outperform a single strong model equipped with best-of-N sampling. We argue that a core source of this instabi…
The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning
Zhanke Zhou, Xiangyu Lu, Chentao Cao +4
RL with verifiable rewards can substantially improve LLM reasoning, yet standard GRPO-style training often treats easy, hard, and learnable questions alike through uniform sampling…
AlphaApollo: A System for Deep Agentic Reasoning
Zhanke Zhou, Chentao Cao, Xiao Feng +15
We present AlphaApollo, an agentic reasoning system that targets two bottlenecks in foundation-model reasoning: (1) limited reasoning capacity for complex, long-horizon problem sol…
Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
Chentao Cao, Xiaojun Xu, Bo Han +1
As large language models (LLMs) continue to advance in capabilities, ensuring their safety against jailbreak attacks remains a critical challenge. In this paper, we introduce a nov…
From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium
Xie Yi, Zhanke Zhou, Chentao Cao +3
Multi-agent frameworks can substantially boost the reasoning power of large language models (LLMs), but they typically incur heavy computational costs and lack convergence guarante…
Noisy Test-Time Adaptation in Vision-Language Models
Chentao Cao, Zhun Zhong, Zhanke Zhou +4
Test-time adaptation (TTA) aims to address distribution shifts between source and target data by relying solely on target data during testing. In open-world scenarios, models often…